{"id":"W4416322339","doi":"10.3390/make7040148","title":"Model-Aware Automatic Benchmark Generation with Self-Error Instructions for Data-Driven Models","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministero dello Sviluppo Economico","keywords":"Benchmark (surveying); Data point; Generative grammar; Regression; Data-driven; Data modeling; Experimental data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00427002,0.001766337,0.000996988,0.001369296,0.0005490695,0.001798096,0.003218587,0.001261124,0.003596749],"category_scores_gemma":[0.02614338,0.0007611934,0.001060433,0.001020143,0.0009594447,0.001976323,0.002154348,0.002763842,0.001152567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371354,"about_ca_system_score_gemma":0.002878155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003866007,"about_ca_topic_score_gemma":0.006804675,"domain_scores_codex":[0.9966349,0.00123227,0.0002609929,0.0007181685,0.0009015727,0.0002521956],"domain_scores_gemma":[0.9845962,0.008336271,0.0008724747,0.003655878,0.002189752,0.0003495168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005736863,0.0008044968,0.01109877,0.0004263511,0.0001639987,0.0003279231,0.0003818355,0.6966406,0.01838717,0.0201851,0.01431418,0.2366958],"study_design_scores_gemma":[0.00002344417,0.00003888974,0.0002079369,0.000009860445,0.000006940013,0.00001580987,0.00001381711,0.990234,0.004729073,0.00404211,0.0006690916,0.000008977969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05816122,0.0001959322,0.9079359,0.0002653069,0.0001262173,0.0003881708,0.0007132466,0.03035285,0.001861147],"genre_scores_gemma":[0.4368851,0.00008564488,0.5553957,0.0002043761,0.00003404588,0.0009066618,0.00270274,0.00271002,0.001075719],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00427002,"threshold_uncertainty_score":0.02258229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05107415529911185,"score_gpt":0.3329024960587661,"score_spread":0.2818283407596542,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}